检索结果-内蒙古大学图书馆

Meta-Radiology 2025年第1期3卷

作者： Li, Meizhi Wu, Shangjie Liang, Xiao Gao, Chuanqi Hu, Muhua Chen, Zhu He, Pei Jia, Tingting Xiong, Li Department of Pulmonary and Critical Care Medicine The Second Xiangya Hospital of Central South University Changsha China Department of Medical Administration The Second Xiangya Hospital of Central South University Changsha China Clinical Medical Research Center for Pulmonary and Critical Care Medicine in Hunan Province Changsha China Hunan Research Centre for Evidence-based Medicine The Second Xiangya Hospital of Central South University Changsha China Department of Biomedical Engineering School of Basic Medical Science Central South University Changsha China Department of Radiology Second Xiangya Hospital Central South University Changsha China Hunan Key Laboratory for Super Microstructure and Ultrafast Process School of Physics and Electronics Central South University Changsha China National Engineering Research Center for Medical Big Data Application Technology and Big Data Institute Central South University Changsha China General Surgery Department of Second Xiangya Hospital Central South University Changsha China General Surgery Intelligent Healthcare Division of Clinical Medical Research Center of Hunan Province Changsha China

Four-dimensional (4D) flow Magnetic Resonance Imaging (MRI) technology has emerged as a valuable tool in angiography, offering unique insights into the hemodynamics and flow patterns. This research aims to explore the role of 4D flow MRI in advancing our understanding of Deep Vein Thrombosis (DVT), covering its applications in diagnosing, characterizing and mechanism of DVT, as well as its potential for guiding treatment strategies. The qualitative and quantitative information provided by 4D flow MRI enables a comprehensive assessment of blood flow in different vascular regions, shedding light on the relationship between hemodynamic changes and the onset and progression of vascular diseases. Nevertheless, most quantitative research findings for 4D hemodynamic indicators are lacking, and their use is mainly limited to examining arterial conditions. More exploration will be necessary to determine their applicability in studying venous vessels. © 2025 The Authors

关键词： 4D flow MRI Deep vein thrombosis Image analysis algorithms Noninvasive imaging

来源：评论

学校读者我要写书评

暂无评论

Travel Time Delay Model of Mixed Traffic Flow Considering Different Dedicated Lane Management Policies for Cavs

SSRN

引用

SSRN 2024年

作者： Ren, Tingting Yao, Zhihong Jiang, Yangsheng School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Sichuan Chengdu611756 China

To investigate the impact of dedicated lane management policies for connected automated vehicles (CAVs) on travel time delay, this paper proposes a general framework of the travel time delay model considering different dedicated lane management policies for CAVs. First, the car-following modes and their proportions in CAVs dedicated lanes and normal lanes with different dedicated lane management policies are analyzed, and the average time headways are further derived. Second, the travel time delay model with sufficiently high demand and low/medium demand is derived based on the point queue (P-Q) model, respectively. Then, the relevant properties of the travel time delay model with different dedicated lane management policies for CAVs are proposed and proved. Finally, multiple parameters, such as traffic saturation, the penetration rate of CAVs, and the arrival rate of vehicles, are adopted to discuss their impact on the optimal split ratio, traffic capacity, average reduced delay, optimal CAVs penetration rate interval, optimal CAVs penetration rate, and optimal lane management policy. Results show that (1) when the traffic saturation is less than or equal to 1, the optimal split ratio is always 0;when the traffic saturation is greater than 1, the optimal split ratio remains 0 first and then increases with the CAVs penetration rate;(2) the average reduced delay of (C, M) and (C, H) policies is always 0 when the traffic saturation is less than or equal to 1, and the average delay of (C, M) and (C, H) policies is minimum 0.63 times that of the mixed traffic flow without CAVs dedicated lanes;(3) the optimal CAVs penetration rate to reduce the average delay most for both (C, M) and (C, H) policies first increases to and then remains unchanged with the increase of traffic saturation. In particular, the optimal CAVs penetration rate for (C, M) and (C, H) policies is always 0.53 when the traffic saturation is more than or equal to 1.79 and 2.24, respectively;(4) only when

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Cooperative Merging for Connected Automated Vehicles in Mixed Traffic: A Multi-Agent Reinforcement Learning Approach

SSRN

引用

SSRN 2023年

作者： Sun, Zhanbo Huang, Jiayi Ji, Ang Zhao, Ruibin Zheng, Guoqian School of Transportation and Logistics Southwest Jiaotong University Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China

The paper investigates the cooperative decision-making for mixed traffic (CDMMT) ramp merging problem based on a multi-agent reinforcement learning (MARL) approach. With the help of V2X technology, autonomous agents exchange information and corresponding strategies throughout the learning procedure, which can align individual interests with the system’s efficiency. To further improve the driving performance of autonomous agents, expert demonstrations for car-following and merging actions are exploited to diminish collisions at the beginning of the training process, the Multi-Agent Proximal Policy Optimization (MAPPO) with a curriculum learning process is then designed to learn strategies from scenarios with various flow conditions and achieve fast and stable convergence. The simulation results indicate that, compared to human-driven vehicles behaving in over-competitive or conservative strategies, MARL-based agents can improve traffic efficiency by 57.9% in a fully saturated situation. In addition, it is found that, even with 10% CAV penetration, the overall traffic efficiency can be improved by 11.8%. Furthermore, as the mainline traffic flow increases, mainline vehicles prioritize efficiency over safety. In contrast, ramp vehicles exhibit a more conservative behavior, emphasizing safety in response to crowded mainline traffic. Finally, the simulation experiments with different demand splits, penetration rates, and traffic densities reveal the model’s potential learning and transferring capabilities in dynamic traffic conditions, which can hopefully offer valuable insights for future research related to CDMMT problems. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Robust Control For Connected Automated Vehicle Platoon With Multiple-Predecessor Following Topology Considering Communication Loss

SSRN

引用

SSRN 2024年

作者： Yang, Lei Sun, Zhanbo Liu, Yafei Chen, Linbin School of Transportation and Logistics Southwest Jiaotong University Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China

The paper presents a robust control method for effectively managing uncertainties and communication loss in a connected automated vehicle (CAV) platoon under the multiple-predecessor following (MPF) topology. The proposed approach incorporates uncertainties in vehicle dynamics, such as vehicle parameters and environmental resistances, into the closed-loop platoon system to enhance the robustness of the platoon controller. The impacts of communication loss are analyzed specifically for the MPF topology, considering potential disruptions in information flow among different numbers and locations of predecessors in a CAV platoon. A novel formulation of desired spacing, suitable for the CAV platoon with MPF topology under communication loss, is then developed based on the constant time headway (CTH) policy. Furthermore, the paper derives and proves the sufficient and necessary conditions for the local stability of the proposed robust platoon controller using Kharitonov's theorem. The sufficient conditions for string stability are also discussed through frequency-domain analysis. These conditions establish the stability region for the robust controller of a CAV platoon with varying locations and numbers of unconnected predecessors. Simulation experiments are conducted to demonstrate that the stability region of the controller diminishes as the number of unconnected predecessors increases, with the greatest impact observed when the communication with the nearest connected predecessor is lost. Additionally, the control performance is affected by uncertain dynamics and the range of time headway, resulting in a significant reduction in the stability region. The findings highlight the importance of fine-tuning control parameters within the stability region guided by the derived stability conditions to ensure both local and string stability of CAV platoons. © 2024, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

面向排放测算的随机性对跟驰模型车队稳定性的影响研究

引用

Journal of Central South University 2023年第8期30卷 2772-2789页

作者：孟冬利宋国华鲁洪语吴亦政翟志强于雷 Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong UniversityBeijing 100044China School of Civil and Environmental Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Department of Transportation Studies Texas Southern UniversityHoustonTX 77004USA

在基于微观交通仿真模型进行交通能耗排放评估时,跟驰模型生成的车辆轨迹无法代表实际交通环境的驾驶特性,从而导致显著的排放测算误差,同时车辆排放在车队中的稳定性未被充分考虑。本文基于真实的车队轨迹比较了Gipps跟驰模型、全速差... 详细信息

在基于微观交通仿真模型进行交通能耗排放评估时,跟驰模型生成的车辆轨迹无法代表实际交通环境的驾驶特性,从而导致显著的排放测算误差,同时车辆排放在车队中的稳定性未被充分考虑。本文基于真实的车队轨迹比较了Gipps跟驰模型、全速差模型(FVDM)、智能驾驶员模型(IDM)和Wiedemann模型的面向排放测算的车队稳定性,分析了参数敏感性和随机性对跟驰模型的影响,提出了考虑随机参数的Gipps跟驰模型。结果表明,与Wiedemann模型相比,FVD模型和IDM模型在排放测算方面的误差较小,并且上述三个模型的排放测算误差沿车队是稳定的。Gipps模型能够真实地刻画车队中第一辆跟驰车的车辆动力学,但排放测算误差沿车队逐渐增大。参数敏感性分析表明模型参数标定难以提高Gipps模型的车队稳定性。结合随机参数对Gipps跟驰模型进行优化后,加速度分布均方根误差、VSP分布均方根误差和排放因子相对误差分别降低了5.00%、2.52%和11.04%,车队误差的标准差分别为0.18%、0.08%和0.86%,这表明随机参数能够提高Gipps跟驰模型面向排放测算的车队稳定性,提升仿真轨迹用于车辆能耗排放评估的准确性。

关键词：跟驰模型车队稳定性随机性排放测算 VSP分布

来源：评论

学校读者我要写书评

暂无评论

Research on Platform Door Setting of Suburban Railway of Mass Transit Type 5th

Research on Platform Door Setting of Suburban Railway of Mas...

引用

5th International Conference on Smart Vehicular technology, transportation, Communication and applications, VTCA 2022

作者： Wenxin, Zhang Yilin, Yang Qingguo, Song Chengli, Zhu Ni, Shaoquan School of Transportation and Logistics Southwest Jiaotong University Chengdu611756 China China Railway Chengdu Bureau Group Co. Ltd. Chengdu610082 China Yibin Railway Industry Investment Co. Ltd. Yibin644000 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China National and Local Joint Engineering Laboratory for Intelligent Integrated Transportation Chengdu611756 China

ISBN: (纸本)9789819908479

The special function orientation and passenger flow characteristics of suburban railway put forward higher demands for its transportation organization, such as mass transit type, rapidness, diversification, and convenience. Under the condition of suburban railway of mass transit type, the characteristics of high density in and out of high-speed trains will affect the safety of waiting and landing at passenger platforms. Based on the current passenger organization and technical level, this paper discussed the necessity and technical feasibility of setting platform door in suburban railway. The results show that the installation of platform door can greatly improve the passenger experience, and the technical conditions for the development of platform door system in suburban railway have been met. It is suggested that the new suburban railway should consider the installation of platform gate or reserve the engineering conditions for the installation of platform gate. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Monotonicity-Induced Health Indicator for Axle-Box Bearings of Urban Rail Vehicles 6th

Monotonicity-Induced Health Indicator for Axle-Box Bearings ...

引用

6th International Conference on Electrical engineering and Information Technologies for Rail transportation, EITRT 2023

作者： Wang, Yiran Xin, Ge An, Guoping Li, Yilei School of Traffic and Transportation Beijing Jiaotong University Beijing100044 China Center of Safety Technology National Railway Administration Beijing100160 China School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789819993147

Health indicators of axle-box bearings play an important role in failure prediction for urban rail vehicles. Vibration-based signal processing technology is a promising tool to reveal the degradation process with fruitful time-frequency information. However, the processes usually have non-stationary features caused by complex working conditions, which may be confused with the unknown temporal variations under different frequency bands. To address this issue, this paper proposes a new index, named monotonicity-induced health indicator, which is adaptive to weight the optimal frequency bands. First, frequency domain analysis is used to extract features from vibration signals. The monotonicity of these features is then estimated and their weights are optimized by means of maximizing the monotonicity. Eventually, all the features and weights are fused together to obtain a health indicator. The experimental result proves that the proposed health indicator shows its superiority in terms of monotonicity while accurately characterizing the degradation process of the bearings. © 2024, Beijing Paike Culture Commu. Co., Ltd.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling of Single-Line Electric Buses with Battery Swapping

Optimal Scheduling of Single-Line Electric Buses with Batter...

引用

IEEE International Conference on Intelligent transportation engineering (ICITE)

作者： Yuyan Guo Tao Liu National Engineering Laboratory of Integrated Transportation Big Data Application Technology Institute of System Science and Engineering School of Transportation and Logistics Southwest Jiaotong University Chengdu China

ISBN: (数字)9798350314212

ISBN: (纸本)9798350314229

With the advantages of zero emission and comfortable riding experience, battery-electric buses (BEBs) are widely adopted in public transit agencies as a green alternative to conventional diesel buses. Battery swapping technology is an efficient and promising charging technology to address the issues of battery range anxiety and long battery charging time. This study developed a two-stage optimization model to optimize the single-line battery-electric bus scheduling problem considering battery swapping. At the first stage, a bi-objective integer programming model is established to determine the minimum BEB fleet size, together with the BEB-to-trip assignment and battery swapping schedule. At the second stage, an integer linear programming model is formulated to determine the required minimum number of batteries. An $\epsilon$ -constraint method is designed to investigate the trade-off between the required minimum fleet size and the number of back-up batteries. Finally, a real-world case study of a BEB line in Chengdu, China, is conducted to demonstrate the effectiveness of the optimization model and solution method. Sensitivity analyses are further conducted to understand the impacts of some key parameters, including battery capacity, number of trips, cycle time, and battery swapping time. The results show that battery capacity and cycle time have significant influences on BEB-to-trip assignment results and battery swapping schedule.

关键词： Integer programming Schedules Sensitivity analysis Optimization models transportation Stochastic processes Optimal scheduling Integer linear programming Scheduling Batteries

来源：评论

学校读者我要写书评

暂无评论

Survival Analysis of Logistics Service Providers: An Empirical Study of Chengdu, Area in China

引用

Open Journal of Statistics 2020年第6期10卷 915-935页

作者： Guoqi Li Yihuan Tu Lihao Duan Jin Zhang Lei Huang Wanshan Wu Zhuoshi Lv School of Transportation and Logistics Southwest Jiaotong University Chengdu Sichuan China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu China National United Engineering Laboratory of Integrated and Intelligent Transportation Chengdu China School of Mathematics Southwest Jiaotong University Chengdu China

This paper worked on a sample of 6791 logistics establishments registered in Chengdu, China over the period 1984-2016 to understand the survival status of logistics service providers (LSPs) by non-parametric Kaplan-Meier estimation, together with Cox proportional hazard regression model, to identify factors affecting the failure of LSPs. In particular, it studies the interaction effect between LSPs’ size and entry timing and location. The empirical results show that: 1) Regarding the survival time, 1365 of the 6791 sample LSPs exited from the market by 2017. The exit rate is 20.1%, and the average life of the 6791 LSPs is about 6 years. 2) The survival of LSPs depends on their typology, ownership structure. And there is no significant difference in the probability of survival for both independent LSPs and logistics branches after controlling the effects of other variables. 3) Location and entry timing also play an important role in the survival of small-scale LSPs, but these factors cannot explain large-scale LSPs’ failure.

关键词： Logistics Service Providers Survival Analysis Kaplan-Meier Estimation Cox Proportional Hazard Regression

来源：评论

学校读者我要写书评

暂无评论

MSLKCNN: A Simple and Powerful Multi-scale Large Kernel CNN for Hyperspectral Image Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Liu, Xun Ng, Alex Hay-Man Lei, Fangyuan Ren, Jinchang Guo, Li Du, Zheyuan Guangdong University of Technology School of Information Engineering Guangzhou510006 China Guangdong University of Technology School of Civil and Transportation Engineering Guangzhou510006 China Guangdong Polytechnic Normal University Guangdong Provincial Key Laboratory of Intellectual Property Big Data Guangzhou510665 China Robert Gordon University National Subsea Centre AberdeenAB21 0BH United Kingdom Ministry of Natural Resources Land Satellite Remote Sensing Application Center Beijing100048 China Geoscience Australia Canberra2609 Australia University of New South Wales School of Civil and Environmental Engineering SydneyNSW2052 Australia

Deep learning-based hyperspectral image (HSI) classification models typically utilize multiple feature extraction layers to learn the features of land covers. Nevertheless, they encounter challenges, e.g., 1) Transformers require substantial computational resources, and 2) these layers are carefully assembled and designed. Recently, large kernel convolutional neural networks (LKCNNs) show excellent performance in natural visual tasks. To tackle these limitations and explore the capability of LKCNNs for HSI classification, we present a novel simple and powerful multi-scale large kernel convolutional neural network architecture (MSLKCNN) with the largest kernel size as large as 15 × 15, in contrast to commonly used 3 × 3, for HSI classification. MSLKCNN avoids these specialized designs, comprising a noise suppression module (NSM) and a multi-scale large kernel convolution (MSLKC). Specifically, NSM is first used to suppress the noise and reduce the number of the bands before extracting the features. Then, MSLKC, as the only feature extraction layer of MSLKCNN, joints three parallel convolutions to capture the features of various types (i.e. spectral, spectral-spatial) and ranges (i.e., small local, larger local, and global) from the dimension of scale: (C1) convolution with a kernel size of 1 × 1 is used to extract spectral features;(C2) multi-scale large kernel depthwise separable convolution (MLKDC) is proposed to learn the spectral-spatial features of different ranges including short-range, middle-range, and long-range;and (C3) multi-scale dilated depthwise separable convolution (MDDC) is designed to aggregate the spectral-spatial features between land covers at various distances. Extensive experimental results on three public HSI datasets demonstrate the competitiveness of the proposed MSLKCNN compared with several state-of-the-art methods. © 1980-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：